twitter_bookmark_tweet

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag readOnlyHint=false, so the description adds value by specifying the side-effect scope: the bookmark lands only in the authenticated account's *private* bookmarks, and the operation is reversible via twitter_unbookmark_tweet. It also discloses the auth requirement ('write capability behind your key'). It stops short of 5 because, with no output schema, it doesn't disclose return/error behavior or duplicate-bookmark semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core action, then input form, precondition, and reversal — every sentence earns its place with zero filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers action, account scope, privacy, input form (id or url), auth precondition, and reversal, while the schema's property descriptions add proxy/auth pairing nuances. The only gap is that no output schema exists and the description doesn't hint at return values or already-bookmarked behavior; for such a simple write operation this is a minor omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 — the property descriptions already document the id/url mutual exclusion ('Provide exactly one of id or url'), ct0/auth_token pairing, proxy_url recommendation for writes, and header mappings. The top-level description merely restates 'Provide the tweet id or url' and adds no syntax or format detail beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource+scope: 'Bookmark a tweet to YOUR authenticated account's private bookmarks.' It distinguishes from siblings by scoping the action to the caller's own account and explicitly naming the reverse tool (twitter_unbookmark_tweet), while the read-only bookmark siblings (twitter_bookmarks, twitter_bookmark_search) are clearly different operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when this tool applies: it requires 'write capability behind your key' and names twitter_unbookmark_tweet as the explicit reverse/undo path. However, it doesn't explicitly state when NOT to use this versus the read-only bookmark tools (twitter_bookmarks, twitter_bookmark_search), so it falls just short of full exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.